Dr. Sheenam Khuttan
About me
Sheenam is a computational chemist and Research Scientist specializing in physics-based drug discovery and AI-augmented molecular design. She holds a Ph.D. in Biochemistry from the City University of New York, where she developed novel alchemical free energy methods for predicting drug-protein binding — work that has since been adopted by multiple pharmaceutical organizations and integrated into widely used open-source simulation software. Currently serving as Computational Chemistry Lead at Manas AI, she bridges artificial intelligence and medicinal chemistry through rigorous molecular modeling, with a focus on discovering therapeutics against previously undruggable disease targets. She has authored seven peer-reviewed publications in leading chemistry journals and has been recognized for top-ranked performance in international computational chemistry benchmarks.
Sheenam is a computational chemist and Research Scientist with over seven years of experience at the intersection of chemical sciences, molecular biophysics, and AI-driven drug discovery. She holds a Ph.D. in Biochemistry from the City University of New York, where her doctoral research focused on developing and validating alchemical free energy perturbation methods — a class of physics-based computational techniques used to predict how strongly drug molecules bind to disease-relevant proteins. This work laid the foundation for a novel methodology that has since been independently adopted by multiple biopharmaceutical organizations and integrated as an official plugin into OpenMM, one of the most widely used open-source molecular simulation platforms in the world.
Following her doctorate, Sheenam joined SandboxAQ as a Postdoctoral Researcher and was subsequently promoted to Research Scientist, where she led ML-augmented free energy perturbation pipelines across therapeutic programs in oncology, neurodegeneration, and GPCR biology. She played a key role in deploying computational workflows that reduced animal use and experimental costs in antibody optimization campaigns, and built end-to-end modeling pipelines on GPU-accelerated cloud infrastructure. She currently serves as Computational Chemistry Lead at Manas AI, where she bridges artificial intelligence and medicinal chemistry through rigorous physics-based modeling, with a dedicated focus on undruggable targets — proteins implicated in cancer and other serious diseases that conventional drug design approaches cannot address.
Sheenam has authored seven peer-reviewed publications in leading journals including the Journal of Chemical Theory and Computation, Journal of Chemical Information and Modeling, and the Journal of Chemical Physics, accumulating over 200 citations. She has achieved first and second-place rankings in the SAMPL international blind prediction challenges, the gold standard for prospective benchmarking in computational chemistry, and has contributed to the field as a peer reviewer for 14 manuscripts including those submitted to Nature Communications. She also serves as Lead Guest Editor for a special collection in the Journal of Chemical Research and has been recognized with multiple academic scholarships and a full membership in the Sigma Xi Scientific Research Honor Society.
